Dynamical structure function identifiability conditions enabling signal structure reconstruction

Networks of controlled dynamical systems exhibit a variety of interconnection patterns that could be interpreted as the structure of the system. One such interpretation of system structure is a system's signal structure, characterized as the open-loop causal dependencies among manifest variables and represented by its dynamical structure function. Although this notion of structure is among the weakest available, previous work has shown that if no a priori structural information is known about the system, not even the Boolean structure of the dynamical structure function is identifiable. Consequently, one method previously suggested for obtaining the necessary a priori structural information is to leverage knowledge about target specificity of the controlled inputs. This work extends these results to demonstrate precisely the a priori structural information that is both necessary and sufficient to reconstruct the network from input-output data. This extension is important because it significantly broadens the applicability of the identifiability conditions, enabling the design of network reconstruction experiments that were previously impossible due to practical constraints on the types of actuation mechanisms available to the engineer or scientist. The work is motivated by the proteomics problem of reconstructing the Per-Arnt-Sim Kinase pathway used in the metabolism of sugars. © 2012 IEEE.

Identifiability of diffusion and sorption parameters from in situ diffusion experiments by using simultaneously tracer dilution and claystone data

In situ diffusion experiments are performed in geological formations at underground research laboratories to overcome the limitations of laboratory diffusion experiments and investigate scale effects. Tracer concentrations are monitored at the injection interval during the experiment (dilution data) and measured from host rock samples around the injection interval at the end of the experiment (overcoring data). Diffusion and sorption parameters are derived from the inverse numerical modeling of the measured tracer data. The identifiability and the uncertainties of tritium and Na-22(+) diffusion and sorption parameters are studied here by synthetic experiments having the same characteristics as the in situ diffusion and retention (DR) experiment performed on Opalinus Clay. Contrary to previous identifiability analyses of in situ diffusion experiments, which used either dilution or overcoring data at approximate locations, our analysis of the parameter identifiability relies simultaneously on dilution and overcoring data, accounts for the actual position of the overcoring samples in the claystone, uses realistic values of the standard deviation of the measurement errors, relies on model identification criteria to select the most appropriate hypothesis about the existence of a borehole disturbed zone and addresses the effect of errors in the location of the sampling profiles. The simultaneous use of dilution and overcoring data provides accurate parameter estimates in the presence of measurement errors, allows the identification of the right hypothesis about the borehole disturbed zone and diminishes other model uncertainties such as those caused by errors in the volume of the circulation system and the effective diffusion coefficient of the filter. The proper interpretation of the experiment requires the right hypothesis about the borehole disturbed zone. A wrong assumption leads to large estimation errors. The use of model identification criteria helps in the selection of the best model. Small errors in the depth of the overcoring samples lead to large parameter estimation errors. Therefore, attention should be paid to minimize the errors in positioning the depth of the samples. The results of the identifiability analysis do not depend on the particular realization of random numbers. (C) 2012 Elsevier B.V. All rights reserved.

Testing Independence in High Dimensions & Identifiability of Graphical Models

Thesis (Ph.D.)--University of Washington, 2016-06

Identifiability and definiteness in Chinese

This article explores how the pragmatic notion of identfiability is encoded in Chinese. It presents a detailed analysis of the distinctive linguistic devices, including lexical, morphological, and position in sentence, which are employed in Chinese to indicate the interpretation of referents in respect of identifiability. Of the major determiners in Chinese, demonstratives are developing uses of a definite article, and yi 'one' + classier has developed uses of an indefinite article, although morphologically and in some cases also functionally they have not yet been fully grammaticalized. What makes Chinese further different from languages like English is the interpretation in this regard of what are called indeterminate lexical encodings, which include bare NPs and cardinality expressions. They by themselves are neutral in respect of the interpretation of identifiability. For indeterminate expressions, there is a strong but seldom absolute correlation between the interpretation of identiability or nonidentfiability and their occurrence in different positions in a sentence. Unlike the cases with several other languages without articles like Czech, Hindi, and Indonesian, the features of definiteness and indefiniteness cannot be obligatorily and uniquely specified for nominal expressions in Chinese. The findings in this article lead to the conclusion that definiteness as a grammatical category defined in the narrow sense has not been fully developed in Chinese.

A Parameter Estimation and Identifiability Analysis Methodology Applied to a Street Canyon Air Pollution Model

Mathematical models are increasingly used in environmental science thus increasing the importance of uncertainty and sensitivity analyses. In the present study, an iterative parameter estimation and identifiability analysis methodology is applied to an atmospheric model – the Operational Street Pollution Model (OSPMr). To assess the predictive validity of the model, the data is split into an estimation and a prediction data set using two data splitting approaches and data preparation techniques (clustering and outlier detection) are analysed. The sensitivity analysis, being part of the identifiability analysis, showed that some model parameters were significantly more sensitive than others. The application of the determined optimal parameter values was shown to succesfully equilibrate the model biases among the individual streets and species. It was as well shown that the frequentist approach applied for the uncertainty calculations underestimated the parameter uncertainties. The model parameter uncertainty was qualitatively assessed to be significant, and reduction strategies were identified.

Consistent HMM parameter estimation using Kerridge inaccuracy rates

In this paper, we propose a novel online hidden Markov model (HMM) parameter estimator based on Kerridge inaccuracy rate (KIR) concepts. Under mild identifiability conditions, we prove that our online KIR-based estimator is strongly consistent. In simulation studies, we illustrate the convergence behaviour of our proposed online KIR-based estimator and provide a counter-example illustrating the local convergence properties of the well known recursive maximum likelihood estimator (arguably the best existing solution).

Modeling of the hemodynamic responses in block design fMRI studies

The hemodynamic response function (HRF) describes the local response of brain vasculature to functional activation. Accurate HRF modeling enables the investigation of cerebral blood flow regulation and improves our ability to interpret fMRI results. Block designs have been used extensively as fMRI paradigms because detection power is maximized; however, block designs are not optimal for HRF parameter estimation. Here we assessed the utility of block design fMRI data for HRF modeling. The trueness (relative deviation), precision (relative uncertainty), and identifiability (goodness-of-fit) of different HRF models were examined and test-retest reproducibility of HRF parameter estimates was assessed using computer simulations and fMRI data from 82 healthy young adult twins acquired on two occasions 3 to 4 months apart. The effects of systematically varying attributes of the block design paradigm were also examined. In our comparison of five HRF models, the model comprising the sum of two gamma functions with six free parameters had greatest parameter accuracy and identifiability. Hemodynamic response function height and time to peak were highly reproducible between studies and width was moderately reproducible but the reproducibility of onset time was low. This study established the feasibility and test-retest reliability of estimating HRF parameters using data from block design fMRI studies.

Overfitting Bayesian mixture models with an unknown number of components

This paper proposes solutions to three issues pertaining to the estimation of finite mixture models with an unknown number of components: the non-identifiability induced by overfitting the number of components, the mixing limitations of standard Markov Chain Monte Carlo (MCMC) sampling techniques, and the related label switching problem. An overfitting approach is used to estimate the number of components in a finite mixture model via a Zmix algorithm. Zmix provides a bridge between multidimensional samplers and test based estimation methods, whereby priors are chosen to encourage extra groups to have weights approaching zero. MCMC sampling is made possible by the implementation of prior parallel tempering, an extension of parallel tempering. Zmix can accurately estimate the number of components, posterior parameter estimates and allocation probabilities given a sufficiently large sample size. The results will reflect uncertainty in the final model and will report the range of possible candidate models and their respective estimated probabilities from a single run. Label switching is resolved with a computationally light-weight method, Zswitch, developed for overfitted mixtures by exploiting the intuitiveness of allocation-based relabelling algorithms and the precision of label-invariant loss functions. Four simulation studies are included to illustrate Zmix and Zswitch, as well as three case studies from the literature. All methods are available as part of the R package Zmix, which can currently be applied to univariate Gaussian mixture models.

Toiminta ja tarkoite : Tutkimus suomen pronominista

The study describes the use and meaning of the Finnish demonstrative pronouns, focus being on the pronoun "tämä" (roughly 'this'). The Finnish demonstrative system is a three way one, the other two demonstratives are "tuo" ('that') and "se" ('it'). The data consisted of 12 half hours of video- and tape-recorded face-to-face and telephone conversations. The method for the study was ethnomethodological conversation analysis (CA); in addition to CA, the theoretical framework consisted of functional linguistics and linguistic anthropology. First, the study dealt with the syntactic distribution of the three demonstratives. The pronouns were analysed according to whether they are before or after the verb, and whether they compose an NP on their own or are determinants of a lexical NP. The study suggested that the form and the placement of the NP presents the referent as continuous/discontinuous or given/new. Givenness of a referent was defined as "identified adequately for the purposes of the on-going action". The so-called dislocated utterances were considered separately. It was found that left-dislocations are used for inserting referents in a particular relation to the on-going activity. Right-dislocations offer a solution for the sometimes competing motivations of newness and continuity: they are used for securing the identifiability of a referent that is implied to be continuous. Second, the study focussed on analysing the meaning of the pronouns according to three dimensions of reference: referential, indexical and relational. It was found that the demonstratives can organize interactional or spatial context. When organizing interactional context, the demonstrative pronouns express the role of identifying the referent in relation to the on-going activity. The pronoun "tämä" expresses that the referent is referentially open and the characterization of the referent is given in the on-going turn. Furthermore, it expresses asymmetry of the indexical ground: it expresses that the participants of a conversation do not share a mutual understanding of the activity at that particular time. In addition, the referent of the pronoun "tämä" is central for understanding the on-going action. Centrality could be understood as the relational feature of the pronoun. However, it is a consequence of the referential and indexical features of "tämä". The pronoun "tuo" also expresses referential openness, but it implies indexical symmetry. The pronoun "se" implies that the referent is known enough, and implies indexical symmetry. When used spatially, the pronouns may refer to a physical space or to a situation. They express or imply that the speaker is inside or outside the referent. The pronoun "tämä" implies inclusion, and the pronoun "tuo" expresses exclusion.